Update README.md

README.md

@@ -18,27 +18,23 @@ Usage:
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
-from peft import PeftModel
 
 
-tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/baichuan-7B", trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("baichuan-inc/baichuan-7B", device_map="auto", trust_remote_code=True)
-model = PeftModel.from_pretrained(model, "hiyouga/baichuan-7b-sft")
+tokenizer = AutoTokenizer.from_pretrained("hiyouga/baichuan-7b-sft", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("hiyouga/baichuan-7b-sft", trust_remote_code=True).cuda()
 streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
 
 query = "晚上睡不着怎么办"
+template = "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.\nHuman: {}\nAssistant: "
 
-inputs = tokenizer(["<human>:{}\n<bot>:".format(query)], return_tensors="pt")
+inputs = tokenizer([template.format(query)], return_tensors="pt")
 inputs = inputs.to("cuda")
 generate_ids = model.generate(**inputs, max_new_tokens=256, streamer=streamer)
 ```
 
 You could also alternatively launch a CLI demo by using the script in https://github.com/hiyouga/LLaMA-Efficient-Tuning
 ```bash
-python src/cli_demo.py \
-    --model_name_or_path baichuan-inc/baichuan-7B \
-    --checkpoint_dir hiyouga/baichuan-7b-sft \
-    --prompt_template ziya
+python src/cli_demo.py --model_name_or_path hiyouga/baichuan-7b-sft
 ```
 
 Loss curve on training set: